Back to leaderboard

qwen3-vl:4b-instruct

OLLAMA GGUF

qwen3vl · 4.4B · Q4_K_M

Excellent

Apr 20, 2026 · Apple M2 Max

qwen3.5:9b

OLLAMA GGUF

qwen35 · 9.7B · Q4_K_M

Marginal

Mar 5, 2026 · Apple M1 Max

Global Score
83 vs 53
Hardware Fit
96 vs 72
Quality Score
78 vs 45

Hardware

qwen3-vl:4b-instruct qwen3.5:9b
MachineMac StudioMacBook Pro
CPUApple M2 MaxApple M1 Max
Cores1210
RAM96 GB32 GB
GPUApple M2 MaxApple M1 Max
OSmacOS 26.1macOS 26.3
Archarm64arm64
Power Modebalancedbalanced

Performance

qwen3-vl:4b-instruct qwen3.5:9b
Tokens/sec90.618.6
First chunk159 ms403 ms
TTFT159 ms10.2 s
Load time5.8 s4.3 s
Memory usage42.5 GB9.1 GB
Memory %44%28%

HW Fit Score Breakdown

qwen3-vl:4b-instruct

Speed
50/50
TTFT
20/20
Memory
26/30

qwen3.5:9b

Speed
38/50
TTFT
4/20
Memory
30/30

Quality

qwen3-vl:4b-instruct

Reasoning
14/20
Coding
16/20
Instruction
16/20
Structured
15/15
Math
8/15
Multilingual
9/10
Reasoning: Adequate Coding: Strong Instruction Following: Strong Structured Output: Strong Math: Adequate Multilingual: Strong

qwen3.5:9b

Reasoning
12/20
Coding
3/20
Instruction
5/20
Structured
6/15
Math
11/15
Multilingual
8/10
Reasoning: Adequate Coding: Poor Instruction Following: Weak Structured Output: Weak Math: Adequate Multilingual: Strong
View qwen3-vl:4b-instruct details | View qwen3.5:9b details

Run yours and compare

$ npm install -g metrillm@latest
$ metrillm

Requires Node 20+ and Ollama or LM Studio running

Or run without installing: npx metrillm@latest